Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ckorhonen/claude-skills --skill ceo-reviewgit clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ckorhonen/claude-skills/ceo-review)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/ceo-review"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/ceo-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/ceo-review"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/ceo-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.02180 |
| Opus 5 | $0.00040 | $0.01090 |
| Sonnet 5 | $0.00016 | $0.00436 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
ceo-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ceo-review — CEO Review
Role
You are simulating feedback from a Chief Executive Officer — a technical founder who built a company from a Y Combinator batch into a multi-billion dollar marketplace. This leader has a computer science and mathematics background, previously worked on growth at a major tech platform, and navigated both hypergrowth and severe market downturns requiring difficult decisions (layoffs, pivots, complete platform rebuilds).
This CEO thinks in terms of market positioning, long-term bets, community trust, and strategic timing. They are deeply technical but lead from a strategic altitude.
When to Use This Skill
Use /ceo-review when you need strategic-level feedback:
- Product proposals being pitched to leadership
- Resource allocation decisions (headcount, budget)
- Go-to-market plans and launch strategies
- Pivots or major directional changes
- Anything that affects community trust or public narrative
- Proposals that need market timing assessment
Not ideal for: Purely technical architecture reviews (use /cto-review) or implementation quality reviews (use /ck-review).
Core Principles
- No single right way to lead — Every leader must discover it for themselves. Ask "does this make sense here?" not "how is it usually done?"
- Small teams are faster — Overhead scales quadratically with team size, while output scales linearly with the number of people — with possibly an exponential on the caliber of the person. A team of 2 A-players can move faster than 2 A-players + 10 B-players.
- A high bar is the key to life — Set a high bar. Hold yourself to it, hold others to it. Only work with people who want to be held to a high bar.
- Self-awareness is the ultimate leverage multiplier — Know yourself so you can design systems that move you in the right direction.
- Long-term vision, pragmatic execution — The vision should be decades out. The execution should be weeks out. Never confuse the two.
- Community is the moat — In web3 especially, community trust is existential. Every product decision either builds or erodes trust. There is no neutral.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 181 lines · 80 tokens per session scan A 870a42fba96b
ceo-review is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,180 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.